|
|
Data Analysis for Predictive Maintenance of a Robotic Arm
Žitný, Roland ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The Mitsubishi MELFA robotic arms used in modern factories work almost without interruption and produce sensory data about their operation. Various analysis techniques can be applied to such data for predictive maintenance, which provide information on the condition and maintenance needs of such robotic arms. The proposed predictive maintenance process consists of a sensory data acquisition system using the slmpclient and mitsubishi-monitor libraries, an analysis method system with anomaly detection using a convolutional autoencoder, anomaly classification using convolutional neural networks, and data segmentation into segments of individual robot actions using hidden Markov models. Such analysis techniques provide information on the severity, type, and location of emerging faults and abnormalities in behavior, which then determine the time required to perform the required maintenance. This work presents a created chain of predictive maintenance processes, where the obtained findings provide valuable insights into the application of predictive maintenance of Mitsubishi MELFA robotic arms in an industrial environment.
|
|
| |
|
|
Code Generation from Object Oriented Petri Nets
Cibák, Michal ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
The goal of this thesis is to analyze the current solution of a code generator from Object oriented Petri nets written in PNtalk language to Java language, propose changes and implement them. First the overall scheme was analyzed and missing parts were specified, then the source code of the compiler was analyzed and errors were found. After implementing the fixes for these errors, it was proposed to modify the compiler and simulator such that the missing functionality was supported. These changes were implemented.
|
|
|
Sequence Diagram Generation from Object-Oriented Petri Nets
Beňo, Adam ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
The thesis focuses on the issue of sequence diagram generation from scenarios modelled by object-oriented Petri nets (OOPN). It aims on module implementation into existing OOPN editor which enables showing sequence diagrams from individual simulations and is connected with simulated model. The user thus gets complete overview of the simulation process and is able to detect errors in OOPN models.
|
|
|
City Traffic Simulator for Web
Kováč, Kristián ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
The goal of this thesis is to create a city traffic simulator, which visualizes its results on a web interface. Information about the traffic network is obtained from the OpenStreetMap project. The simulation is based on a microscopic model and focuses mainly on the Brno - Střed area. Vehicles are modeled as separate entities that communicate with each other and follow the traffic rules. The thesis describes the basic principles of traffic modeling and simulation. It also deals with some existing microscopic traffic simulators and their properties. The second part of the thesis describes the design and implementation of the created application. It focuses mainly on the description of OpenStreetMap data processing, vehicle model, structure of simulation results and their visualization on a web interface.
|
|
|
UWB Locator
Jančiar, Marek ; Kočí, Radek (referee) ; Janoušek, Vladimír (advisor)
The subject of this work is the implementation and evaluation of the parameters of the localization system using UWB technology. This work focuses on two localization methods, namely TWR and TDoA. To compare the capabilities of UWB with other wireless techno- logy, this work also includes an implementation using BLE technology, specifically a method that uses the RSSI value. Parameters such as the accuracy or energy consumption of the implementation of these methods on specific hardware were practically measured and in- corporated into the text of this work. With the help of this work, the reader can create an image of the capabilities of the mentioned technologies and the way of implementing the localization methods.
|
|
|
Visualizing Neuroevolution in Neural Network Learning
Bednář, Martin ; Janoušek, Vladimír (referee) ; Zbořil, František (advisor)
This thesis examines options for neural network learning achieved by means of neuroevolution, examines general functioning of neuroevolution, design and implementation of neuroevolution and marginally deals with design and implementation of feed-forward neural networks with fully connected layers. The goal of this thesis is to introduce program, that executes neuroevolutionary algorithm and separate graphic application, which encapsulates this program for easier use and for display of graphic output of the program visualizing problem-solving capabilities of neural networks created by neuroevolution. The end part of the thesis is devoted to experiments done on the created program.
|
|
|
Test Suite of the EAS Framework
Mazáková, Júlia ; Janoušek, Vladimír (referee) ; Smrčka, Aleš (advisor)
Toto dielo sa zameriava na softvérové testovanie systému s dôrazom na nižšie vrstvy testovania, ktoré zahŕňajú testovanie jednotlivých komponent a integráciu. Hlavným cieľom je demonštrovať proces testovania na EAS (Efektívny Agendový Systém), začínajúc plánovaním testov a následne vytvorením konečnej testovacej sady, ktorá vyhodnocuje výkon mikroslužieb systému. Táto testovacia sada pokrýva významnú časť funkcionality systému. Výsledky sú zobrazené a analyzované vo vygenerovanej testovacej správe. Analyzovanie systému a konečný report slúžia ako cenný nástroj v rámci testovania.
|
|
|
Nástroj pro editaci a běh řídicích panelů pro IoT aplikace
Ryška, Andrej ; Peringer, Petr (referee) ; Janoušek, Vladimír (advisor)
This bachelor thesis analyses existing open source solutions for IoT devices with a focus on the presentation, processing and manipulation of data through the user interface of a web application. The goal of this thesis is to implement a custom solution based on the analysis, preferring simplicity, ease of configuration and user friendliness. The implemented application is to be compatible with Node-RED, Domoticz and Home Assistant via an MQTT broker, from which the application will draw data and manipulate the states of individual IoT devices
|
|
|
Deep Learning Methods for Machine Playing the Scotland Yard Board Game
Hrkľová, Zuzana ; Janoušek, Vladimír (referee) ; Zbořil, František (advisor)
Táto práca sa zaoberá metódami hlbokého učenia, ktoré sú aplikovateľné na stolné hry s neurčitosťou. V rámci práce boli naštudované princípy učenia s posilňovaním, s hlavným zameraním na Q-learning algoritmy, spomedzi ktorých bol vybraný Deep Q-Network algoritmus. Ten bol následne implementovaný na zjednodušených pravidlách stolnej hry Scotland Yard. Konečná implementácia bola porovnaná s metódami Alpha-Beta a Monte Carlo Tree Search. S výsledkov vyplinulo, že schovávaný hráč riadený DQN algoritmom predstavoval pre ostatné metódy najťažšieho protihráča, narozdiel od hľadajúcich hráčov, ktorým sa nepodarilo zlepšiť existujúce riešenia. Napriek tomu, že implementovaná metóda nedosiahla lepšie výsledky oproti doposiaľ existujúcim metódam, ukázalo sa, že potrebuje najmenej výpočetných zdrojov a času na vykonanie daného ťahu. To ju robí najperspektívnejšou zo spomínaných metód na budúcu možnú implementáciu originálnej verzie danej hry.
|
guest ::
